© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117399
    Prev
    Next
    INDEX
    Explanations

    phrases starting with common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     screenshot
    -1.38
    Screenshot
    -1.34
    ﻷ
    -1.32
     SqlConnection
    -1.28
    ﻻ
    -1.24
     ulike
    -1.23
     également
    -1.20
     endforeach
    -1.20
     bì
    -1.20
     recaudación
    -1.18
    POSITIVE LOGITS
     seldom
    1.46
    部份
    1.30
     usually
    1.28
     almost
    1.25
     someplace
    1.17
     дуже
    1.13
     Usually
    1.13
     dramatically
    1.12
    ◆◇
    1.10
     even
    1.09
    Activations Density 0.058%

    No Known Activations